1 Markov Logic Stanley Kok Dept. of Computer Science & Eng. University of Washington Joint work with Pedro Domingos, Daniel Lowd, Hoifung Poon, Matt Richardson, Parag Singla and Jue Wang

2 Overview Motivation Background Markov logic Inference Learning Software Applications

3 Motivation Most learners assume i.i.d. data (independent and identically distributed) One type of object Objects have no relation to each other Real applications: dependent, variously distributed data Multiple types of objects Relations between objects

4 Examples Web search Medical diagnosis Computational biology Social networks Information extraction Natural language processing Perception Ubiquitous computing Etc.

5 Costs/Benefits of Markov Logic Benefits Better predictive accuracy Better understanding of domains Growth path for machine learning Costs Learning is much harder Inference becomes a crucial issue Greater complexity for user

6 Overview Motivation Background Markov logic Inference Learning Software Applications

7 Markov Networks Undirected graphical models Cancer CoughAsthma Smoking Potential functions defined over cliques SmokingCancer Ф(S,C) False 4.5 FalseTrue 4.5 TrueFalse 2.7 True 4.5

8 Markov Networks Undirected graphical models Log-linear model: Weight of Feature iFeature i Cancer CoughAsthma Smoking

9 Hammersley-Clifford Theorem If Distribution is strictly positive (P(x) > 0) And Graph encodes conditional independences Then Distribution is product of potentials over cliques of graph Inverse is also true. (“Markov network = Gibbs distribution”)

10 Markov Nets vs. Bayes Nets PropertyMarkov NetsBayes Nets FormProd. potentials PotentialsArbitraryCond. probabilities CyclesAllowedForbidden Partition func.Z = ?Z = 1 Indep. checkGraph separationD-separation Indep. props.Some InferenceMCMC, BP, etc.Convert to Markov

11 First-Order Logic Constants, variables, functions, predicates E.g.: Anna, x, MotherOf(x), Friends(x, y) Literal: Predicate or its negation Clause: Disjunction of literals Grounding: Replace all variables by constants E.g.: Friends (Anna, Bob) World (model, interpretation): Assignment of truth values to all ground predicates

12 Overview Motivation Background Markov logic Inference Learning Software Applications

13 Markov Logic: Intuition A logical KB is a set of hard constraints on the set of possible worlds Let’s make them soft constraints: When a world violates a formula, It becomes less probable, not impossible Give each formula a weight (Higher weight  Stronger constraint)

14 Markov Logic: Definition A Markov Logic Network (MLN) is a set of pairs (F, w) where F is a formula in first-order logic w is a real number Together with a set of constants, it defines a Markov network with One node for each grounding of each predicate in the MLN One feature for each grounding of each formula F in the MLN, with the corresponding weight w

15 Example: Friends & Smokers

16 Example: Friends & Smokers

17 Example: Friends & Smokers

18 Example: Friends & Smokers Two constants: Anna (A) and Bob (B)

19 Example: Friends & Smokers Cancer(A) Smokes(A)Smokes(B) Cancer(B) Two constants: Anna (A) and Bob (B)

20 Example: Friends & Smokers Cancer(A) Smokes(A)Friends(A,A) Friends(B,A) Smokes(B) Friends(A,B) Cancer(B) Friends(B,B) Two constants: Anna (A) and Bob (B)

21 Example: Friends & Smokers Cancer(A) Smokes(A)Friends(A,A) Friends(B,A) Smokes(B) Friends(A,B) Cancer(B) Friends(B,B) Two constants: Anna (A) and Bob (B)

22 Example: Friends & Smokers Cancer(A) Smokes(A)Friends(A,A) Friends(B,A) Smokes(B) Friends(A,B) Cancer(B) Friends(B,B) Two constants: Anna (A) and Bob (B)

23 Markov Logic Networks MLN is template for ground Markov nets Probability of a world x : Typed variables and constants greatly reduce size of ground Markov net Functions, existential quantifiers, etc. Infinite and continuous domains Weight of formula iNo. of true groundings of formula i in x

24 Relation to Statistical Models Special cases: Markov networks Markov random fields Bayesian networks Log-linear models Exponential models Max. entropy models Gibbs distributions Boltzmann machines Logistic regression Hidden Markov models Conditional random fields Obtained by making all predicates zero-arity Markov logic allows objects to be interdependent (non-i.i.d.)

25 Relation to First-Order Logic Infinite weights  First-order logic Satisfiable KB, positive weights  Satisfying assignments = Modes of distribution Markov logic allows contradictions between formulas

26 Overview Motivation Background Markov logic Inference Learning Software Applications

27 MAP/MPE Inference Problem: Find most likely state of world given evidence QueryEvidence

28 MAP/MPE Inference Problem: Find most likely state of world given evidence

29 MAP/MPE Inference Problem: Find most likely state of world given evidence

30 MAP/MPE Inference Problem: Find most likely state of world given evidence This is just the weighted MaxSAT problem Use weighted SAT solver (e.g., MaxWalkSAT [Kautz et al., 1997] ) Potentially faster than logical inference (!)

31 The WalkSAT Algorithm for i ← 1 to max-tries do solution = random truth assignment for j ← 1 to max-flips do if all clauses satisfied then return solution c ← random unsatisfied clause with probability p flip a random variable in c else flip variable in c that maximizes number of satisfied clauses return failure

32 The MaxWalkSAT Algorithm for i ← 1 to max-tries do solution = random truth assignment for j ← 1 to max-flips do if ∑ weights(sat. clauses) > threshold then return solution c ← random unsatisfied clause with probability p flip a random variable in c else flip variable in c that maximizes ∑ weights(sat. clauses) return failure, best solution found

33 But … Memory Explosion Problem: If there are n constants and the highest clause arity is c, the ground network requires O(n ) memory Solution: Exploit sparseness; ground clauses lazily → LazySAT algorithm [Singla & Domingos, 2006] c

34 Computing Probabilities P(Formula|MLN,C) = ? MCMC: Sample worlds, check formula holds P(Formula1|Formula2,MLN,C) = ? If Formula2 = Conjunction of ground atoms First construct min subset of network necessary to answer query (generalization of KBMC) Then apply MCMC (or other) Can also do lifted inference [Braz et al, 2005]

35 Ground Network Construction network ← Ø queue ← query nodes repeat node ← front(queue) remove node from queue add node to network if node not in evidence then add neighbors(node) to queue until queue = Ø

36 MCMC: Gibbs Sampling state ← random truth assignment for i ← 1 to num-samples do for each variable x sample x according to P(x|neighbors(x)) state ← state with new value of x P(F) ← fraction of states in which F is true

37 But … Insufficient for Logic Problem: Deterministic dependencies break MCMC Near-deterministic ones make it very slow Solution: Combine MCMC and WalkSAT → MC-SAT algorithm [Poon & Domingos, 2006]

38 Overview Motivation Background Markov logic Inference Learning Software Applications

39 Learning Data is a relational database Closed world assumption (if not: EM) Learning parameters (weights) Learning structure (formulas)

40 Generative Weight Learning Maximize likelihood Numerical optimization (gradient or 2 nd order) No local maxima Requires inference at each step (slow!) No. of times clause i is true in data Expected no. times clause i is true according to MLN

41 Pseudo-Likelihood Likelihood of each variable given its neighbors in the data Does not require inference at each step Widely used in vision, spatial statistics, etc. But PL parameters may not work well for long inference chains

42 Discriminative Weight Learning Maximize conditional likelihood of query ( y ) given evidence ( x ) Approximate expected counts with: counts in MAP state of y given x (with MaxWalkSAT) with MC-SAT No. of true groundings of clause i in data Expected no. true groundings of clause i according to MLN

43 Structure Learning Generalizes feature induction in Markov nets Any inductive logic programming approach can be used, but... Goal is to induce any clauses, not just Horn Evaluation function should be likelihood Requires learning weights for each candidate Turns out not to be bottleneck Bottleneck is counting clause groundings Solution: Subsampling

44 Structure Learning Initial state: Unit clauses or hand-coded KB Operators: Add/remove literal, flip sign Evaluation function: Pseudo-likelihood + Structure prior Search: Beam, shortest-first, bottom-up [Kok & Domingos, 2005; Mihalkova & Mooney, 2007]

45 Overview Motivation Background Markov logic Inference Learning Software Applications

46 Alchemy Open-source software including: Full first-order logic syntax Generative & discriminative weight learning Structure learning Weighted satisfiability and MCMC Programming language features alchemy.cs.washington.edu

47 Overview Motivation Background Markov logic Inference Learning Software Applications

48 Applications Basics Logistic regression Hypertext classification Information retrieval Entity resolution Bayesian networks Etc.

49 Running Alchemy Programs Infer Learnwts Learnstruct Options MLN file Types (optional) Predicates Formulas Database files

50 Uniform Distribn.: Empty MLN Example: Unbiased coin flips Type: flip = { 1, …, 20 } Predicate: Heads(flip)

51 Binomial Distribn.: Unit Clause Example: Biased coin flips Type: flip = { 1, …, 20 } Predicate: Heads(flip) Formula: Heads(f) Weight: Log odds of heads: By default, MLN includes unit clauses for all predicates (captures marginal distributions, etc.)

52 Multinomial Distribution Example: Throwing die Types: throw = { 1, …, 20 } face = { 1, …, 6 } Predicate: Outcome(throw,face) Formulas: Outcome(t,f) ^ f != f’ => !Outcome(t,f’). Exist f Outcome(t,f). Too cumbersome!

53 Multinomial Distrib.: ! Notation Example: Throwing die Types: throw = { 1, …, 20 } face = { 1, …, 6 } Predicate: Outcome(throw,face!) Formulas: Semantics: Arguments without “!” determine arguments with “!”. Also makes inference more efficient (triggers blocking).

54 Multinomial Distrib.: + Notation Example: Throwing biased die Types: throw = { 1, …, 20 } face = { 1, …, 6 } Predicate: Outcome(throw,face!) Formulas: Outcome(t,+f) Semantics: Learn weight for each grounding of args with “+”.

55 Logistic regression: Type: obj = { 1,..., n } Query predicate: C(obj) Evidence predicates: F i (obj) Formulas: a C(x) b i F i (x) ^ C(x) Resulting distribution: Therefore: Alternative form: F i (x) => C(x) Logistic Regression

56 Text Classification page = { 1, …, n } word = { … } topic = { … } Topic(page,topic!) HasWord(page,word) !Topic(p,t) HasWord(p,+w) => Topic(p,+t)

57 Text Classification Topic(page,topic!) HasWord(page,word) HasWord(p,+w) => Topic(p,+t)

58 Hypertext Classification Topic(page,topic!) HasWord(page,word) Links(page,page) HasWord(p,+w) => Topic(p,+t) Topic(p,t) ^ Links(p,p') => Topic(p',t) Cf. S. Chakrabarti, B. Dom & P. Indyk, “Hypertext Classification Using Hyperlinks,” in Proc. SIGMOD-1998.

59 Information Retrieval InQuery(word) HasWord(page,word) Relevant(page) InQuery(+w) ^ HasWord(p,+w) => Relevant(p) Relevant(p) ^ Links(p,p’) => Relevant(p’) Cf. L. Page, S. Brin, R. Motwani & T. Winograd, “The PageRank Citation Ranking: Bringing Order to the Web,” Tech. Rept., Stanford University, 1998.

60 Problem: Given database, find duplicate records HasToken(token,field,record) SameField(field,record,record) SameRecord(record,record) HasToken(+t,+f,r) ^ HasToken(+t,+f,r’) => SameField(+f,r,r’) SameField(f,r,r’) => SameRecord(r,r’) SameRecord(r,r’) ^ SameRecord(r’,r”) => SameRecord(r,r”) Cf. A. McCallum & B. Wellner, “Conditional Models of Identity Uncertainty with Application to Noun Coreference,” in Adv. NIPS 17, Entity Resolution

61 Can also resolve fields: HasToken(token,field,record) SameField(field,record,record) SameRecord(record,record) HasToken(+t,+f,r) ^ HasToken(+t,+f,r’) => SameField(f,r,r’) SameField(f,r,r’) SameRecord(r,r’) SameRecord(r,r’) ^ SameRecord(r’,r”) => SameRecord(r,r”) SameField(f,r,r’) ^ SameField(f,r’,r”) => SameField(f,r,r”) More: P. Singla & P. Domingos, “Entity Resolution with Markov Logic”, in Proc. ICDM Entity Resolution

62 Bayesian Networks Use all binary predicates with same first argument (the object x). One predicate for each variable A: A(x,v!) One conjunction for each line in the CPT A literal of state of child and each parent Weight = log P(Child|Parents) Context-specific independence: One conjunction for each path in the decision tree Logistic regression: As before

63 Practical Tips Add all unit clauses (the default) Implications vs. conjunctions Open/closed world assumptions Controlling complexity Low clause arities Low numbers of constants Short inference chains Use the simplest MLN that works Cycle: Add/delete formulas, learn and test

64 Summary Most domains are non-i.i.d. Markov logic combines first-order logic and probabilistic graphical models Syntax: First-order logic + Weights Semantics: Templates for Markov networks Inference: LazySAT + MC-SAT Learning: LazySAT + MC-SAT + ILP + PL Software: Alchemy